期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：237
期号：3
页码：032043
DOI：10.1088/1755-1315/237/3/032043
出版社：IOP Publishing
摘要：Since it is inevitable existence of unknown mutation signals, gross error and data missing in the GPS station coordinates, while the nonlinear signals and misalignment are also neglected by means of piecewise linear detection, thus a novel algorithm called jump determination scheme, which is based on singular spectrum analysis (SSA), is proposed here. The results of real data analysis and simulation tests indicate that the SSA-based pre-processing method has properly detected the gross error and recovered the missing data. Meanwhile, owing to taking into account the correlation in the position time series, it can effectively avoid the influence of gross error on the accurate determination of each uncertain jump. In addition, it can retain the intrinsic characteristics in station coordinates, which has vital significance for the gross error detection and missing data recovery. By this new method, even if the missing rate of data reaches 10% or more, we can eliminate the gross error and then obtain complete data with an accuracy of better than 5 mm and 1 cm for the horizontal components and the height component, respectively.
